Python 你的答案比其他人好。 Select a.col1, b.col2 from tb1 as a inner join tb2 as b on tb1.col7 = tb2.col8; tb1 col1 tb1 col7 tb2 col2 tb2 col8

你的答案比其他人好。

Select a.col1, b.col2 from tb1 as a inner join tb2 as b on tb1.col7 = tb2.col8;

tb1 col1
tb1 col7
tb2 col2
tb2 col8

import ply.lex as lex, re

tokens = (
    "TABLE",
    "JOIN",
    "COLUMN",
    "TRASH"
)

tables = {"tables": {}, "alias": {}}
columns = []

t_TRASH = r"Select|on|=|;|\s+|,|\t|\r"

def t_TABLE(t):
    r"from\s(\w+)\sas\s(\w+)"

    regex = re.compile(t_TABLE.__doc__)
    m = regex.search(t.value)
    if m is not None:
        tbl = m.group(1)
        alias = m.group(2)
        tables["tables"][tbl] = ""
        tables["alias"][alias] = tbl

    return t

def t_JOIN(t):
    r"inner\s+join\s+(\w+)\s+as\s+(\w+)"

    regex = re.compile(t_JOIN.__doc__)
    m = regex.search(t.value)
    if m is not None:
        tbl = m.group(1)
        alias = m.group(2)
        tables["tables"][tbl] = ""
        tables["alias"][alias] = tbl
    return t

def t_COLUMN(t):
    r"(\w+\.\w+)"

    regex = re.compile(t_COLUMN.__doc__)
    m = regex.search(t.value)
    if m is not None:
        t.value = m.group(1)
        columns.append(t.value)
    return t

def t_error(t):
    raise TypeError("Unknown text '%s'" % (t.value,))
    t.lexer.skip(len(t.value))

# here is where the magic starts
def mylex(inp):
    lexer = lex.lex()
    lexer.input(inp)

    for token in lexer:
        pass

    result = {}
    for col in columns:
        tbl, c = col.split('.')
        if tbl in tables["alias"].keys():
            key = tables["alias"][tbl]
        else:
            key = tbl

        if key in result:
            result[key].append(c)
        else:
            result[key] = list()
            result[key].append(c)

    print result
    # {'tb1': ['col1', 'col7'], 'tb2': ['col2', 'col8']}    

string = "Select a.col1, b.col2 from tb1 as a inner join tb2 as b on tb1.col7 = tb2.col8;"
mylex(string)

import re

def tables_in_query(sql_str):

    # remove the /* */ comments
    q = re.sub(r"/\*[^*]*\*+(?:[^*/][^*]*\*+)*/", "", sql_str)

    # remove whole line -- and # comments
    lines = [line for line in q.splitlines() if not re.match("^\s*(--|#)", line)]

    # remove trailing -- and # comments
    q = " ".join([re.split("--|#", line)[0] for line in lines])

    # split on blanks, parens and semicolons
    tokens = re.split(r"[\s)(;]+", q)

    # scan the tokens. if we see a FROM or JOIN, we set the get_next
    # flag, and grab the next one (unless it's SELECT).

    tables = set()
    get_next = False
    for tok in tokens:
        if get_next:
            if tok.lower() not in ["", "select"]:
                tables.add(tok)
            get_next = False
        get_next = tok.lower() in ["from", "join"]

    dictTables = dict()
    for table in tables:
        fields = []
        for token in tokens:
            if token.startswith(table):
                if token != table:
                    fields.append(token)
        if len(list(set(fields))) >= 1:
        dictTables[table] = list(set(fields))
    return dictTables

>>> sql_metadata.get_query_columns("SELECT test, id FROM foo, bar")
[u'test', u'id']

>>> sql_metadata.get_query_tables("SELECT test, id FROM foo, bar")
[u'foo', u'bar']

>>> sql_metadata.get_query_limit_and_offset('SELECT foo_limit FROM bar_offset LIMIT 50 OFFSET 1000')
(50, 1000)

>>> parse("SELECT id,name FROM dual WHERE id>3 and id<10 ORDER BY name")
{'select': [{'value': 'id'}, {'value': 'name'}], 'from': 'dual', 'where': {'and': [{'gt': ['id', 3]}, {'lt': ['id', 10]}]}, 'orderby': {'value': 'name'}}

import pandas as pd
#%config PPMagics.autolimit=0


#txt = """<your SQL text here>"""
txt_1 = txt
replace_list = ['\n', '(', ')', '*', '=','-',';','/','.']
count = 0
for i in replace_list:
    txt_1 = txt_1.replace(i, ' ')
txt_1 = txt_1.split()
res = []
for i in range(1, len(txt_1)):
    if txt_1[i-1].lower() in ['from', 'join','table'] and txt_1[i].lower() != 'select': 
        count +=1
        str_count = str(count)
        res.append(txt_1[i] + "." + txt_1[i+1])


#df.head()
res_l = res
f_res_l = []
for i in range(0,len(res_l)):
    if len(res_l[i]) > 15 : # change it to 0 is you want all the caught strings
        f_res_l.append(res_l[i])
    else :
        pass

All_Table_List = f_res_l
print("All the unique tables from the SQL text, in the order of their appearence in the code : \n",100*'*')
df = pd.DataFrame(All_Table_List,columns=['Tables_Names'])
df.reset_index(level=0, inplace=True)
list_=list(df["Tables_Names"].unique())
df_1_Final = pd.DataFrame(list_,columns=['Tables_Names'])
df_1_Final.reset_index(level=0, inplace=True)
df_1_Final

lst = "select * from table".split(" ")
lst = [item for item in lst if len(item)>0]
table_name = lst[lst.index("from")+1]